AI agents

Agent skills

Control the actions an agent may choose during a conversation.

Before you start

Use a test channel or sample conversation first. Confirm the visible result in ValueChat before applying the setup to production traffic.

How it works

  1. 01

    Enable only the skills the role needs

    Enable only the skills the role needs.

  2. 02

    Configure each skill target and allowed fields

    Configure each skill target and allowed fields.

  3. 03

    The model chooses between enabled actions from their contracts

    The model chooses between enabled actions from their contracts.

  4. 04

    ValueChat performs permission checks before execution

    ValueChat performs permission checks before execution.

What to verify

✓The expected channel, conversation, contact or execution is visible.

✓The assigned person or agent matches the routing rule.

✓No customer-facing message claims an action that failed.

✓Activity or execution history contains enough context to investigate.

Need help?

Collect the workspace, channel, conversation and execution identifiers, then contact support@valuechat.app. Never send API keys or passwords.